423A35C7/pytorch3d
1
0
Fork 0
mirror of https://github.com/facebookresearch/pytorch3d.git synced 2025-08-02 11:52:50 +08:00
Code Issues Packages Projects Releases Wiki Activity

lint fixes

Browse Source 
Summary: Resolved trailing whitespace warnings.

Reviewed By: gkioxari

Differential Revision: D21023982

fbshipit-source-id: 14ea2ca372c13cfa987acc260264ca99ce44c461
This commit is contained in:
Nikhila Ravi 2020-04-15 21:56:48 -07:00 committed by Facebook GitHub Bot
parent 3794f6753f
commit b530b0af32
3 changed files with 12 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
pytorch3d/loss/point_mesh_distance.py
View File

@ -41,10 +41,10 @@ class _PointFaceDistance(Function):
in the corresponding example in the batch in the corresponding example in the batch
idxs: LongTensor of shape `(P,)` indicating the closest triangular face idxs: LongTensor of shape `(P,)` indicating the closest triangular face
in the corresponindg example in the batch. in the corresponindg example in the batch.
`dists[p] = d(points[p], tris[idxs[p], 0], tris[idxs[p], 1], tris[idxs[p], 2])` `dists[p] = d(points[p], tris[idxs[p], 0], tris[idxs[p], 1], tris[idxs[p], 2])`
where `d(u, v0, v1, v2)` is the distance of point `u` from the trianfular face `(v0, v1, v2)` where `d(u, v0, v1, v2)` is the distance of point `u` from the trianfular face `(v0, v1, v2)`
""" """
dists, idxs = _C.point_face_dist_forward( dists, idxs = _C.point_face_dist_forward(
points, points_first_idx, tris, tris_first_idx, max_points points, points_first_idx, tris, tris_first_idx, max_points
@ -91,7 +91,7 @@ class _FacePointDistance(Function):
corresponding example in the batch corresponding example in the batch
idxs: LongTensor of shape `(T,)` indicating the closest point in the idxs: LongTensor of shape `(T,)` indicating the closest point in the
corresponindg example in the batch. corresponindg example in the batch.
`dists[t] = d(points[idxs[t]], tris[t, 0], tris[t, 1], tris[t, 2])`, `dists[t] = d(points[idxs[t]], tris[t, 0], tris[t, 1], tris[t, 2])`,
where `d(u, v0, v1, v2)` is the distance of point `u` from the triangular where `d(u, v0, v1, v2)` is the distance of point `u` from the triangular
face `(v0, v1, v2)`. face `(v0, v1, v2)`.
@ -141,7 +141,7 @@ class _PointEdgeDistance(Function):
corresponding example in the batch corresponding example in the batch
idxs: LongTensor of shape `(P,)` indicating the closest edge in the idxs: LongTensor of shape `(P,)` indicating the closest edge in the
corresponindg example in the batch. corresponindg example in the batch.
`dists[p] = d(points[p], segms[idxs[p], 0], segms[idxs[p], 1])`, `dists[p] = d(points[p], segms[idxs[p], 0], segms[idxs[p], 1])`,
where `d(u, v0, v1)` is the distance of point `u` from the edge segment where `d(u, v0, v1)` is the distance of point `u` from the edge segment
spanned by `(v0, v1)`. spanned by `(v0, v1)`.
@ -191,7 +191,7 @@ class _EdgePointDistance(Function):
corresponding example in the batch corresponding example in the batch
idxs: LongTensor of shape `(S,)` indicating the closest point in the idxs: LongTensor of shape `(S,)` indicating the closest point in the
corresponindg example in the batch. corresponindg example in the batch.
`dists[s] = d(points[idxs[s]], edges[s, 0], edges[s, 1])`, `dists[s] = d(points[idxs[s]], edges[s, 0], edges[s, 1])`,
where `d(u, v0, v1)` is the distance of point `u` from the segment where `d(u, v0, v1)` is the distance of point `u` from the segment
spanned by `(v0, v1)`. spanned by `(v0, v1)`.
@ -226,7 +226,7 @@ def point_mesh_edge_distance(meshes: Meshes, pcls: Pointclouds):
to the closest edge segment in mesh and averages across all points in pcl to the closest edge segment in mesh and averages across all points in pcl
`edge_point(mesh, pcl)`: Computes the squared distance of each edge segment in mesh `edge_point(mesh, pcl)`: Computes the squared distance of each edge segment in mesh
to the closest point in pcl and averages across all edges in mesh. to the closest point in pcl and averages across all edges in mesh.
The above distance functions are applied for all `(mesh, pcl)` pairs in the batch and The above distance functions are applied for all `(mesh, pcl)` pairs in the batch and
then averaged across the batch. then averaged across the batch.
@ -293,7 +293,7 @@ def point_mesh_face_distance(meshes: Meshes, pcls: Pointclouds):
to the closest triangular face in mesh and averages across all points in pcl to the closest triangular face in mesh and averages across all points in pcl
`face_point(mesh, pcl)`: Computes the squared distance of each triangular face in mesh `face_point(mesh, pcl)`: Computes the squared distance of each triangular face in mesh
to the closest point in pcl and averages across all faces in mesh. to the closest point in pcl and averages across all faces in mesh.
The above distance functions are applied for all `(mesh, pcl)` pairs in the batch and The above distance functions are applied for all `(mesh, pcl)` pairs in the batch and
then averaged across the batch. then averaged across the batch.

6
pytorch3d/ops/knn.py
View File

@ -125,7 +125,7 @@ def knn_points(
p1_dists: Tensor of shape (N, P1, K) giving the squared distances to p1_dists: Tensor of shape (N, P1, K) giving the squared distances to
the nearest neighbors. This is padded with zeros both where a cloud in p2 the nearest neighbors. This is padded with zeros both where a cloud in p2
has fewer than K points and where a cloud in p1 has fewer than P1 points. has fewer than K points and where a cloud in p1 has fewer than P1 points.
p2_nn: Tensor of shape (N, P1, K, D) giving the K nearest neighbors in p2 for p2_nn: Tensor of shape (N, P1, K, D) giving the K nearest neighbors in p2 for
each point in p1. Concretely, `p2_nn[n, i, k]` gives the k-th nearest neighbor each point in p1. Concretely, `p2_nn[n, i, k]` gives the k-th nearest neighbor
for `p1[n, i]`. Returned if `return_nn` is True. for `p1[n, i]`. Returned if `return_nn` is True.
@ -134,7 +134,7 @@ def knn_points(
.. code-block:: .. code-block::
p2_nn = knn_gather(p2, p1_idx, lengths2) p2_nn = knn_gather(p2, p1_idx, lengths2)
which is a helper function that allows indexing any tensor of shape (N, P2, U) with which is a helper function that allows indexing any tensor of shape (N, P2, U) with
the indices `p1_idx` returned by `knn_points`. The outout is a tensor the indices `p1_idx` returned by `knn_points`. The outout is a tensor
of shape (N, P1, K, U). of shape (N, P1, K, U).
@ -168,7 +168,7 @@ def knn_gather(
""" """
A helper function for knn that allows indexing a tensor x with the indices `idx` A helper function for knn that allows indexing a tensor x with the indices `idx`
returned by `knn_points`. returned by `knn_points`.
For example, if `dists, idx = knn_points(p, x, lengths_p, lengths, K)` For example, if `dists, idx = knn_points(p, x, lengths_p, lengths, K)`
where p is a tensor of shape (N, L, D) and x a tensor of shape (N, M, D), where p is a tensor of shape (N, L, D) and x a tensor of shape (N, M, D),
then one can compute the K nearest neighbors of p with `p_nn = knn_gather(x, idx, lengths)`. then one can compute the K nearest neighbors of p with `p_nn = knn_gather(x, idx, lengths)`.

4
tests/test_point_mesh_distance.py
View File

@ -132,7 +132,7 @@ class TestPointMeshDistance(TestCaseMixin, unittest.TestCase):
edge: FloatTensor of shape (2, 3) edge: FloatTensor of shape (2, 3)
Returns: Returns:
dist: FloatTensor of shape (1) dist: FloatTensor of shape (1)
If a, b are the start and end points of the segments, we If a, b are the start and end points of the segments, we
parametrize a point p as parametrize a point p as
x(t) = a + t * (b - a) x(t) = a + t * (b - a)
@ -165,7 +165,7 @@ class TestPointMeshDistance(TestCaseMixin, unittest.TestCase):
point: FloatTensor of shape (3) point: FloatTensor of shape (3)
tri: FloatTensor of shape (3, 3) tri: FloatTensor of shape (3, 3)
Returns: Returns:
dist: FloatTensor of shape (1) dist: FloatTensor of shape (1)
""" """
a, b, c = tri.unbind(0) a, b, c = tri.unbind(0)
cross = torch.cross(b - a, c - a) cross = torch.cross(b - a, c - a)